Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | — | 9B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 200k | 128k |
| These models have no shared benchmark scores. | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 49% | — |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 62.3% | — |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | — | 28.5% |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | — | 82.3% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 78.2% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 75% | — |
| Overview | ||
| Company | Anthropic | Z.ai |
| Release date | Feb 24 2025 | Jul 5 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude 3.7 SonnetvsGPT-6.2 AstraCodeGeeX4-ALL-9BvsGPT-6.2 AstraClaude 3.7 SonnetvsGemini 4 HydrogenCodeGeeX4-ALL-9BvsGemini 4 HydrogenClaude 3.7 SonnetvsMuse EmberCodeGeeX4-ALL-9BvsMuse EmberClaude 3.7 SonnetvsGrok 4.7CodeGeeX4-ALL-9BvsGrok 4.7Claude 3.7 SonnetvsDeepSeek-V4.1-Flash-1017CodeGeeX4-ALL-9BvsDeepSeek-V4.1-Flash-1017Claude 3.7 SonnetvsMistral Large 4CodeGeeX4-ALL-9BvsMistral Large 4Frequently asked questions
Claude 3.7 Sonnet and CodeGeeX4-ALL-9B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. CodeGeeX4-ALL-9B shipped 234 days before Claude 3.7 Sonnet, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude 3.7 Sonnet) vs 128k (CodeGeeX4-ALL-9B). Claude 3.7 Sonnet is closed, while CodeGeeX4-ALL-9B is open weight.
Direct benchmark comparisons are unavailable — Claude 3.7 Sonnet and CodeGeeX4-ALL-9B don't publish scores on any of the same benchmarks.